README.md

---
license: apache-2.0
tags:
  - object-detection
  - person-detection
  - rtmdet
  - real-time
  - computer-vision
pipeline_tag: object-detection
---

# rtmdet-s

This is a Hugging Face-compatible port of **rtmdet-s** from [OpenMMLab MMDetection](https://github.com/open-mmlab/mmdetection).

RTMDet is a family of real-time object detectors based on the CSPNeXt architecture. This checkpoint is pretrained on COCO and is particularly well-suited for **person detection** as a first stage before wholebody pose estimation with [RTMW](https://huggingface.co/akore/rtmw-l-384x288).

## Model description

- **Architecture**: CSPNeXt backbone + CSPNeXtPAFPN neck + RTMDetHead
- **Backbone scale**: deepen=0.33, widen=0.5 (~~9M parameters)
- **Input size**: 640×640
- **Classes**: 80 (COCO)
- **Uses custom code** — load with `trust_remote_code=True`

## Usage

```python
from transformers import AutoConfig, AutoModel, AutoImageProcessor
from PIL import Image
import torch

config = AutoConfig.from_pretrained("akore/rtmdet-s", trust_remote_code=True)
model = AutoModel.from_pretrained("akore/rtmdet-s", trust_remote_code=True)
model.eval()

processor = AutoImageProcessor.from_pretrained("akore/rtmdet-s")
image = Image.open("your_image.jpg").convert("RGB")
inputs = processor(images=image, return_tensors="pt")

with torch.no_grad():
    outputs = model(pixel_values=inputs["pixel_values"])

# outputs["boxes"]:  (N, 4) in [x1, y1, x2, y2]
# outputs["scores"]: (N,)
# outputs["labels"]: (N,)  — 0 = person in COCO
print(outputs)
```

## Citation

```bibtex
@misc{lyu2022rtmdet,
  title={RTMDet: An Empirical Study of Designing Real-Time Object Detectors},
  author={Chengqi Lyu and Wenwei Zhang and Haian Huang and Yue Zhou and Yudong Wang and Yanyi Liu and Shilong Zhang and Kai Chen},
  year={2022},
  eprint={2212.07784},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}
```